Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts

by   Bertrand Charpentier, et al.

Accurate estimation of aleatoric and epistemic uncertainty is crucial to build safe and reliable systems. Traditional approaches, such as dropout and ensemble methods, estimate uncertainty by sampling probability predictions from different submodels, which leads to slow uncertainty estimation at inference time. Recent works address this drawback by directly predicting parameters of prior distributions over the probability predictions with a neural network. While this approach has demonstrated accurate uncertainty estimation, it requires defining arbitrary target parameters for in-distribution data and makes the unrealistic assumption that out-of-distribution (OOD) data is known at training time. In this work we propose the Posterior Network (PostNet), which uses Normalizing Flows to predict an individual closed-form posterior distribution over predicted probabilites for any input sample. The posterior distributions learned by PostNet accurately reflect uncertainty for in- and out-of-distribution data – without requiring access to OOD data at training time. PostNet achieves state-of-the art results in OOD detection and in uncertainty calibration under dataset shifts.


page 2

page 7

page 14

page 15

page 18


Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions

Uncertainty awareness is crucial to develop reliable machine learning mo...

Looking at the posterior: on the origin of uncertainty in neural-network classification

Bayesian inference can quantify uncertainty in the predictions of neural...

Learning Posterior and Prior for Uncertainty Modeling in Person Re-Identification

Data uncertainty in practical person reID is ubiquitous, hence it requir...

Locally Learned Synaptic Dropout for Complete Bayesian Inference

The Bayesian brain hypothesis postulates that the brain accurately opera...

Constraining the Reionization History using Bayesian Normalizing Flows

The next generation 21 cm surveys open a new window onto the early stage...

A new framework for experimental design using Bayesian Evidential Learning: the case of wellhead protection area

In this contribution, we predict the wellhead protection area (WHPA, tar...

A Bayesian Convolutional Neural Network for Robust Galaxy Ellipticity Regression

Cosmic shear estimation is an essential scientific goal for large galaxy...

Code Repositories


Posterior Network: Uncertainty Estimation without OOD Samples via Density-Based Pseudo-Counts (Neurips 2020)

view repo

Please sign up or login with your details

Forgot password? Click here to reset